Arao AI
Back to search results

Qwen3.5-4B · Q6_K

Start a discussion
NVIDIA RTX 409024GBStrata v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q6_K) on NVIDIA RTX 4090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

161.44 tok/s

Decode

Decode speed

654.89 tok/s

Prefill

Prefill speed

1.62 s

TTFT

Time to first token

10.5 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_L Decode 174.81 · Prefill 809.7 ·
  2. vLLM · Q4_K_S Decode 181.53 · Prefill 809.47 ·
  3. Strata · Q6_K (current)Decode 161.44 · Prefill 654.89 ·

Core figures

Decode (avg)
161.44 tok/s
Prefill (avg)
654.89 tok/s
TTFT (avg)
1.62 s
VRAM (avg)
10.5 GB
MTP acceptance rate
0.74
TTFB
1.29 GB
Power draw
461.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q6_K
Framework
Strata
Version
v0.45
Context length
4096 tokens
Batch size
512
GPU layers
8
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
10.5 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.4
Power draw
461.5 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-10

    v0.45 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx

    161.44 tok/s

    Decode

    654.89 tok/s

    Prefill

    1.62 s

    TTFT

    10.5 GB

    VRAM

    0.74

    MTP

    461.5 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=1 running model_id=48 at Q6_K